Dynamic input/output linearization using recurrent neural networks
Delgado, A., Kambhampati, C. and Warwick, K. (1996) Dynamic input/output linearization using recurrent neural networks. In: IEEE International Conference on Neural Networks 1996, 3-6 Jun 1996, Washington DC, USA, pp. 1721-1726.
Full text not archived in this repository.
Official URL: http://dx.doi.org/10.1109/ICNN.1996.549160
A dynamic recurrent neural network (DRNN) is used to input/output linearize a control affine system in the globally linearizing control (GLC) structure. The network is trained as a part of a closed loop that involves a PI controller, the goal is to use the network, as a dynamic feedback, to cancel the nonlinear terms of the plant. The stability of the configuration is guarantee if the network and the plant are asymptotically stable and the linearizing input is bounded.